SRQA：用于仿真问答的合成阅读器
SRQA: Synthetic Reader for Factoid Question Answering
摘要：
问答系统可以用深度神经网络回答来自各个领域和形式的问题，但在面对多个证据时仍然缺乏有效的途径。我们引入了一个新的模型称为SRQA，这意味着合成阅读器的模拟问答。该模型从模型结构、优化目标和训练方法三个方面对多文档场景下的问答系统进行了改进，分别对应多层注意（MA）、交叉证据（CE）和对抗训练（AT）。首先，我们提出了一个多层注意力网络，以获得更好的代表性的证据。多层注意力机制在每一层内进行问题与段落之间的交互，使得每一层证据的表征都考虑到问题的需求。其次，我们设计了一个交叉证据策略，在更多的证据中选择答案跨度。改进了优化目标，将所有答案在多个证据中的位置作为训练目标，使模型能够在多个证据之间进行推理。第三，在我们的模型中，除了词嵌入之外，还对高级变量进行了对抗性训练。还提出了一种新的归一化方法对抗扰动，使我们可以共同添加扰动到几个目标变量。作为一种有效的正则化方法，对抗训练增强了模型处理噪声数据的能力。结合这三种策略，我们提高了模型的上下文表示和定位能力，可以从多个证据中综合提取答案跨度。我们在WebQA数据集上进行了SRQA，实验表明，我们的模型优于最先进的模型（我们的模型的最佳模糊分数高达78.56%，提高了约2%）。
英文摘要：
The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We introduce a new model called SRQA, which means Synthetic Reader for Factoid Question Answering. This model enhances the question answering system in the multi-document scenario from three aspects: model structure, optimization goal, and training method, corresponding to Multilayer Attention (MA), Cross Evidence (CE), and Adversarial Training (AT) respectively. First, we propose a multilayer attention network to obtain a better representation of the evidences. The multilayer attention mechanism conducts interaction between the question and the passage within each layer, making the token representation of evidences in each layer takes the requirement of the question into account. Second, we design a cross evidence strategy to choose the answer span within more evidences. We improve the optimization goal, considering all the answers' locations in multiple evidences as training targets, which leads the model to reason among multiple evidences. Third, adversarial training is employed to high-level variables besides the word embedding in our model. A new normalization method is also proposed for adversarial perturbations so that we can jointly add perturbations to several target variables. As an effective regularization method, adversarial training enhances the model's ability to process noisy data. Combining these three strategies, we enhance the contextual representation and locating ability of our model, which could synthetically extract the answer span from several evidences. We perform SRQA on the WebQA dataset, and experiments show that our model outperforms the state-of-the-art models (the best fuzzy score of our model is up to 78.56%, with an improvement of about 2%).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
